arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.16744cs.AIcs.CY
收藏

ShaRP:利用 Shapley 值解释排名与偏好

ShaRP: Explaining Rankings and Preferences with Shapley Values

New York University(纽约大学);Ukrainian Catholic University(乌克兰天主教大学)

Venetia Pliatsika, Joao Fonseca, Kateryna Akhynko, Ivan Shevchenko, Julia Stoyanovich

AI总结:

针对排名任务中分类/回归解释方法不足的问题,提出基于 Shapley 值的 ShaRP 框架,解释特征对排名、top-k 及成对偏好结果的贡献,并通过多维评估验证其实用性。

摘要:

在招聘、大学录取和贷款等关键领域,算法决策通常基于排名。鉴于这些决策对个人、组织和人群的影响,理解这些决策至关重要——以帮助个人提升其排名位置、设计更好的排名程序并确保法律合规。本文认为,SHAP 等用于分类和回归的可解释性方法不足以应对排名任务,并提出了 ShaRP(Shapley Values for Rankings and Preferences,用于排名和偏好的 Shapley 值),这是一个解释特征对排名结果各方面贡献的框架。ShaRP 可为排名(rank)和 top-k 等各种排名特有的收益函数计算特征贡献,还包含一种新颖的、基于 Shapley 值的方法,用于解释成对偏好结果。我们提供了 ShaRP 的灵活实现,能够在基于分数的排名和排序学习(learning-to-rank)任务中,对表格数据上的排名结果和成对结果进行高效、全面的解释。最后,我们为排名可解释性方法开发了一套全面的评估方法,并通过定性、定量和可用性研究表明,我们的排名感知 QoI 提供了互补的洞察、可有效扩展,并帮助用户在实践中解释排名结果。

英文摘要:

Algorithmic decisions in critical domains such as hiring, college admissions, and lending are often based on rankings. Given the impact of these decisions on individuals, organizations, and population groups, it is essential to understand them - to help individuals improve their ranking position, design better ranking procedures, and ensure legal compliance. In this paper, we argue that explainability methods for classification and regression, such as SHAP, are insufficient for ranking tasks, and present ShaRP - Shapley Values for Rankings and Preferences - a framework that explains the contributions of features to various aspects of a ranked outcome. ShaRP computes feature contributions for various ranking-specific profit functions, such as rank and top-k, and also includes a novel Shapley value-based method for explaining pairwise preference outcomes. We provide a flexible implementation of ShaRP, capable of efficiently and comprehensively explaining ranked and pairwise outcomes over tabular data, in score-based ranking and learning-to-rank tasks. Finally, we develop a comprehensive evaluation methodology for ranking explainability methods, showing through qualitative, quantitative, and usability studies that our rank-aware QoIs offer complementary insights, scale effectively, and help users interpret ranked outcomes in practice.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑